scripts/easyocr_extract.py

from __future__ import annotations

import argparse
import sys
from pathlib import Path


def main() -> None:
    if hasattr(sys.stdout, "reconfigure"):
        sys.stdout.reconfigure(encoding="utf-8", errors="replace")
    if hasattr(sys.stderr, "reconfigure"):
        sys.stderr.reconfigure(encoding="utf-8", errors="replace")

    parser = argparse.ArgumentParser(description="Extract Arabic text from page images with EasyOCR.")
    parser.add_argument("--image-dir", required=True, type=Path)
    parser.add_argument("--out", required=True, type=Path)
    args = parser.parse_args()

    image_paths = sorted(args.image_dir.glob("*.png"))
    total = max(len(image_paths), 1)
    print(f"ARABIC_READER_PROGRESS 0 {total}", flush=True)

    import easyocr

    reader = easyocr.Reader(["ar"], gpu=False, verbose=False)
    pieces: list[str] = []
    for index, image_path in enumerate(image_paths, start=1):
        lines = reader.readtext(str(image_path), detail=0, paragraph=True)
        page_text = "\n".join(str(line).strip() for line in lines if str(line).strip())
        if page_text:
            pieces.append(page_text)
        print(f"ARABIC_READER_PROGRESS {index} {total}", flush=True)

    args.out.parent.mkdir(parents=True, exist_ok=True)
    args.out.write_text("\n\n".join(pieces), encoding="utf-8")


if __name__ == "__main__":
    main()